2021 Meeting - Virtual

Actionable Machine Learning for Drug Discovery and Development

Marinka Zitnik, Harvard University

Abstract:

The success of machine learning depends heavily on the choice of features on which the algorithms are applied. For that reason, much of the efforts go into the engineering of informative features. In this talk, I describe our research in learning deep representations that are actionable and allow endpoint users to ask what-if questions and receive robust predictions that can be interpreted meaningfully. These methods specify deep graph neural functions that can flexibly embed data points into an embedding space, optimized to reflect the topology of input data. Our recent theoretical results allow us to augment the embeddings and make them robust and counterfactually fair. I will describe how these methods enabled the repurposing of drugs for an emerging pathogen and led to downstream validation in human cells. Last, I will highlight Therapeutics Data Commons (https://tdcommons.ai), a platform with AI/ML-ready datasets and tasks for therapeutics together with an ecosystem of tools, libraries, leaderboards, and community resources.

Biography: 

Marinka Zitnik is an Assistant Professor at Harvard University with appointments in the Department of Biomedical Informatics, Broad Institute of MIT and Harvard, and Harvard Data Science. Dr. Zitnik's research is at the interface of machine learning and biomedical informatics, focusing on graph representation learning, knowledge graphs, data fusion, and their applications to network biology and therapeutics. Dr. Zitnik has published extensively in top ML venues and leading interdisciplinary journals. She has organized numerous workshops and tutorials in the nexus of AI, deep learning, drug discovery, and medical AI at leading conferences, where she is also in the organizing committees. Her research won numerous best paper and research awards from the International Society for Computational Biology, Bayer Early Excellence in Science Award, a Rising Star Award in Electrical Engineering and Computer Science, and a Next Generation Award in Biomedicine. 

Aligning Human and Machine Intelligence

Matthias Samwald, University of Vienna

Abstract:

Recent years were marked by outstanding advances in the capabilities of artificial intelligence (AI). Deep learning enabled rapid progress on many benchmarks that were previously deemed difficult to tackle for machine learning algorithms, often achieving human-level performance. Models such as GPT-3 demonstrated problem-solving capabilities across a wide range of intelligence tasks.  Given these developments, AI holds the potential to radically transform society through accelerating technological, biomedical, and societal knowledge creation and innovation. The realization of this potential increasingly hinges on our understanding of how to best define, train, measure, interconnect and utilize AI capabilities. The development of a shared ontology of AI tasks and capabilities is instrumental towards achieving such an understanding. In this talk, I will present recent work on the Intelligence Task Ontology, a large-scale ontology with broad coverage of artificial intelligence tasks, benchmarks, and datasets. I will demonstrate how such ontological models can form the foundation for harnessing AI in biomedical research and clinical decision-making.

Biography: 

Matthias Samwald is an associate professor for biomedical informatics and artificial intelligence at the Medical University of Vienna.  His work is focused on speeding up scientific progress and the development of novel, personalized therapies through advanced AI technologies and knowledge-based systems. He co-authored over 100 peer-reviewed publications in the areas of personalized medicine, NLP, graph machine learning, information retrieval, biomedical ontologies, and clinical decision support systems.